From patchwork Thu Mar 28 23:04:01 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Richard Henderson X-Patchwork-Id: 161342 Delivered-To: patch@linaro.org Received: by 2002:a02:c6d8:0:0:0:0:0 with SMTP id r24csp1329096jan; Thu, 28 Mar 2019 16:27:18 -0700 (PDT) X-Google-Smtp-Source: APXvYqwyye9SpCiiG0mQ4UtzG0rviEobwLSpuvCL8Jwp5NlDmdO6IXy6QboEB2LBvfHiCgytZYux X-Received: by 2002:a24:5089:: with SMTP id m131mr2244403itb.60.1553815638732; Thu, 28 Mar 2019 16:27:18 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1553815638; cv=none; d=google.com; s=arc-20160816; b=M50ieod3T7mO97hAGZRspqGnWM5ux/hiYfuqaIFZuFmZNylCiTXhkymOiNHP2jq4CC wNEoEaupmdpUd8ZGgv3POkkNwnlXSlrw1qZnoBt9EoYW05wLY0v0DniXSytDyHjKmmZo Pym2A6jRWpzf7JqKRG3lILaJ/QImp1Sr0VuYwfTnMByxE8EV4HCbRcSTOU8FtECkodyy 5S0aWO3gnlKUptyTm+BFmJ31BK09xcz1a9Qm/0+q7LlCDTkDRlD8XctHmbTLMnWyERld thus/lL4n34IkB37CP0spHb5IBhOOZ0uFxyP/QM4GetjAqnQAotEiJ0bRE6V4gH/yVWE yUQQ== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=sender:errors-to:list-subscribe:list-help:list-post:list-archive :list-unsubscribe:list-id:precedence:subject:references:in-reply-to :message-id:date:to:from:dkim-signature; bh=LAV2e1zcsm8RHqlYaEAOIgb7zIgP9KoVEMcCPxffum4=; b=EB5q7fPUpyYBueQqlgstFXkr4GPFHCUDKlrpDHnRF+HXmc5Cu4UGriKHw/vXFdGWQH w3thoC6wYabAS/ZlsyO4gCYn9o4cJUiq7D4Z24mq/ItIQoKduhIOO3gmNiSJTED5Qj3L igfnUvT8BNHhbFB8oANfwxNceUERfRSyEPtlFXZmU6uTNLYGaYCTOXuvTFYCG0++7/Ay B+9/qjvEe1HOba1xSw6JXp3UhFE2y59EJulfWDgdq+ueoa3h/Jiuaw/68C5mtXdAy+Au hAKmrmubCHeu6Y1cDt7j1dVRrZI3BNprNJcmSGeqS7Pz/f8j2WNzScGXPt+T8OdMfQju YPTA== ARC-Authentication-Results: i=1; mx.google.com; dkim=fail header.i=@linaro.org header.s=google header.b=cuqKbddi; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=fail (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from lists.gnu.org (lists.gnu.org. [209.51.188.17]) by mx.google.com with ESMTPS id z20si159631jan.83.2019.03.28.16.27.18 for (version=TLS1 cipher=AES128-SHA bits=128/128); Thu, 28 Mar 2019 16:27:18 -0700 (PDT) Received-SPF: pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; Authentication-Results: mx.google.com; dkim=fail header.i=@linaro.org header.s=google header.b=cuqKbddi; spf=pass (google.com: domain of qemu-devel-bounces+patch=linaro.org@nongnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom="qemu-devel-bounces+patch=linaro.org@nongnu.org"; dmarc=fail (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: from localhost ([127.0.0.1]:43260 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1h9eQX-000830-V7 for patch@linaro.org; Thu, 28 Mar 2019 19:27:18 -0400 Received: from eggs.gnu.org ([209.51.188.92]:42236) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1h9eKg-0001dn-IC for qemu-devel@nongnu.org; Thu, 28 Mar 2019 19:21:17 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1h9e5F-0003ME-P5 for qemu-devel@nongnu.org; Thu, 28 Mar 2019 19:05:23 -0400 Received: from mail-pg1-x543.google.com ([2607:f8b0:4864:20::543]:41224) by eggs.gnu.org with esmtps (TLS1.0:RSA_AES_128_CBC_SHA1:16) (Exim 4.71) (envelope-from ) id 1h9e5E-0003Ep-Sq for qemu-devel@nongnu.org; Thu, 28 Mar 2019 19:05:17 -0400 Received: by mail-pg1-x543.google.com with SMTP id f6so224762pgs.8 for ; Thu, 28 Mar 2019 16:05:03 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; h=from:to:subject:date:message-id:in-reply-to:references; bh=LAV2e1zcsm8RHqlYaEAOIgb7zIgP9KoVEMcCPxffum4=; b=cuqKbddirT3j1bjCE33Fzut1Z8LWPT1UOfiLbe2hmbZpDY3vz0E2JmSTx3Q4FrB5FA JvEPY7HKFz3WTwhtB4m5qt25rm6hp9ygfx1jPLqYxRjw9sS23kgQXp2rD3RZH/Z6lCL4 v6nFUsP8m7gEtRmHKy1pYg/yHC/NrdtX28v3jjv8SHSqVPJeqG3nqjfVBVkyubhZwlUn esheFb+5h/rhCgM2uNEhZykvMn/SJbRv857bz/ZarrH3CwRK644D1JpYC04DGwBfDxMF /9kgDe5M+5lKvHTMFXuioMIUNqVRHqobgRVzr0P/zZobegigXP7xntUxVBlRwXYLqMqP lQgg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:subject:date:message-id:in-reply-to :references; bh=LAV2e1zcsm8RHqlYaEAOIgb7zIgP9KoVEMcCPxffum4=; b=h42AVK0sDVsRLwOJJP0EOyPOug3T33GW5hGRE72OeKE4XZEpQdUgeS0+1sA0bUkJJf z9D5Vkt1UyKtHpsV2ChgnHAFi8uSdzyAn/gcT3Zc6KTAvgNMEb/BO/gJLGvuHU8lXkiw 5DueVroF7YX90NTneXmib1c8bCG2HLx8PfO1lyn5611boOKaHBEDZuHjVAvj4RxffiUH aeZ2mojVoC6GQ/gj6YLIUwyYyCcc4S0saCIHzU2Op1M6sgqLEf3ytYwvgzYEfZaNED/c I3Tugw3yOieXFxCONiGvc2PDOsKGor7waiaen5v5v6TF4048WuCHc0jXMDivsl7Hozze 436A== X-Gm-Message-State: APjAAAWn0eFd+/h/pV/COm44QdlnAAUyWBH2qsAzKDLpF7YqBDQt1qoc ctrZiipLP9CvNxdZbZy1FC7JKMYs6oI= X-Received: by 2002:a62:480d:: with SMTP id v13mr44501407pfa.125.1553814302286; Thu, 28 Mar 2019 16:05:02 -0700 (PDT) Received: from cloudburst.ASUS (cpe-66-75-72-255.hawaii.res.rr.com. [66.75.72.255]) by smtp.gmail.com with ESMTPSA id f1sm280911pgl.35.2019.03.28.16.05.00 for (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Thu, 28 Mar 2019 16:05:01 -0700 (PDT) From: Richard Henderson To: qemu-devel@nongnu.org Date: Thu, 28 Mar 2019 13:04:01 -1000 Message-Id: <20190328230404.12909-34-richard.henderson@linaro.org> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20190328230404.12909-1-richard.henderson@linaro.org> References: <20190328230404.12909-1-richard.henderson@linaro.org> X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 2607:f8b0:4864:20::543 Subject: [Qemu-devel] [PATCH for-4.1 v2 33/36] cpu: Move the softmmu tlb to CPUNegativeOffsetState X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patch=linaro.org@nongnu.org Sender: "Qemu-devel" We have for some time had code within the tcg backends to handle large positive offsets from env. This move makes sure that need not happen. Indeed, we are able to assert at build time that simple offsets suffice for all hosts. Signed-off-by: Richard Henderson --- include/exec/cpu-defs.h | 22 +++++++++++++------- tcg/aarch64/tcg-target.inc.c | 29 ++++++-------------------- tcg/arm/tcg-target.inc.c | 40 ++++++++---------------------------- tcg/i386/tcg-target.inc.c | 6 ++++-- tcg/mips/tcg-target.inc.c | 39 ++++++++--------------------------- tcg/ppc/tcg-target.inc.c | 30 ++++++++------------------- tcg/riscv/tcg-target.inc.c | 31 +++++++--------------------- tcg/s390/tcg-target.inc.c | 11 +++++----- tcg/sparc/tcg-target.inc.c | 32 +++++++++-------------------- 9 files changed, 74 insertions(+), 166 deletions(-) -- 2.17.1 Reviewed-by: Peter Maydell diff --git a/include/exec/cpu-defs.h b/include/exec/cpu-defs.h index 3971910653..4cde7d611c 100644 --- a/include/exec/cpu-defs.h +++ b/include/exec/cpu-defs.h @@ -178,13 +178,14 @@ typedef struct CPUTLBDesc { /* * Data elements that are per MMU mode, accessed by the fast path. + * The structure is aligned to aid loading the pair with one insn. */ typedef struct CPUTLBDescFast { /* Contains (n_entries - 1) << CPU_TLB_ENTRY_BITS */ uintptr_t mask; /* The array of tlb entries itself. */ CPUTLBEntry *table; -} CPUTLBDescFast; +} CPUTLBDescFast QEMU_ALIGNED(2 * sizeof(void *)); /* * Data elements that are shared between all MMU modes. @@ -211,28 +212,35 @@ typedef struct CPUTLBCommon { /* * The entire softmmu tlb, for all MMU modes. * The meaning of each of the MMU modes is defined in the target code. + * Since this is placed within CPUNegativeOffsetState, the smallest + * negative offsets are at the end of the struct. */ typedef struct CPUTLB { - CPUTLBDescFast f[NB_MMU_MODES]; - CPUTLBDesc d[NB_MMU_MODES]; CPUTLBCommon c; + CPUTLBDesc d[NB_MMU_MODES]; + CPUTLBDescFast f[NB_MMU_MODES]; } CPUTLB; -/* There are target-specific members named "tlb". This is temporary. */ -#define CPU_COMMON CPUTLB tlb_; -#define env_tlb(ENV) (&(ENV)->tlb_) +#define env_tlb(ENV) (&env_neg(ENV)->tlb) + +/* This will be used by TCG backends to compute offsets. */ +#define TLB_MASK_TABLE_OFS(IDX) \ + ((int)offsetof(ArchCPU, neg.tlb.f[IDX]) - (int)offsetof(ArchCPU, env)) #else -#define CPU_COMMON /* Nothing */ +typedef struct CPUTLB { } CPUTLB; #endif /* !CONFIG_USER_ONLY && CONFIG_TCG */ +#define CPU_COMMON /* Nothing */ + /* * This structure must be placed in ArchCPU immedately * before CPUArchState, as a field named "neg". */ typedef struct CPUNegativeOffsetState { + CPUTLB tlb; IcountDecr icount_decr; } CPUNegativeOffsetState; diff --git a/tcg/aarch64/tcg-target.inc.c b/tcg/aarch64/tcg-target.inc.c index 5e6af10faf..ac765137ae 100644 --- a/tcg/aarch64/tcg-target.inc.c +++ b/tcg/aarch64/tcg-target.inc.c @@ -1451,9 +1451,9 @@ static void add_qemu_ldst_label(TCGContext *s, bool is_ld, TCGMemOpIdx oi, label->label_ptr[0] = label_ptr; } -/* We expect to use a 24-bit unsigned offset from ENV. */ -QEMU_BUILD_BUG_ON(offsetof(CPUArchState, tlb_.f[NB_MMU_MODES - 1].table) - > 0xffffff); +/* We expect to use a 7-bit scaled negative offset from ENV. */ +QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) > 0); +QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) < -512); /* Load and compare a TLB entry, emitting the conditional jump to the slow path for the failure case, which will be patched later when finalizing @@ -1463,8 +1463,9 @@ static void tcg_out_tlb_read(TCGContext *s, TCGReg addr_reg, TCGMemOp opc, tcg_insn_unit **label_ptr, int mem_index, bool is_read) { - int mask_ofs = offsetof(CPUArchState, tlb_.f[mem_index].mask); - int table_ofs = offsetof(CPUArchState, tlb_.f[mem_index].table); + int fast_ofs = TLB_MASK_TABLE_OFS(mem_index); + int mask_ofs = fast_ofs + offsetof(CPUTLBDescFast, mask); + int table_ofs = fast_ofs + offsetof(CPUTLBDescFast, table); unsigned a_bits = get_alignment_bits(opc); unsigned s_bits = opc & MO_SIZE; unsigned a_mask = (1u << a_bits) - 1; @@ -1473,24 +1474,6 @@ static void tcg_out_tlb_read(TCGContext *s, TCGReg addr_reg, TCGMemOp opc, TCGType mask_type; uint64_t compare_mask; - if (table_ofs > 0xfff) { - int table_hi = table_ofs & ~0xfff; - int mask_hi = mask_ofs & ~0xfff; - - table_base = TCG_REG_X1; - if (mask_hi == table_hi) { - mask_base = table_base; - } else if (mask_hi) { - mask_base = TCG_REG_X0; - tcg_out_insn(s, 3401, ADDI, TCG_TYPE_I64, - mask_base, TCG_AREG0, mask_hi); - } - tcg_out_insn(s, 3401, ADDI, TCG_TYPE_I64, - table_base, TCG_AREG0, table_hi); - mask_ofs -= mask_hi; - table_ofs -= table_hi; - } - mask_type = (TARGET_PAGE_BITS + CPU_TLB_DYN_MAX_BITS > 32 ? TCG_TYPE_I64 : TCG_TYPE_I32); diff --git a/tcg/arm/tcg-target.inc.c b/tcg/arm/tcg-target.inc.c index 04c2eebb41..4a8c12e9a4 100644 --- a/tcg/arm/tcg-target.inc.c +++ b/tcg/arm/tcg-target.inc.c @@ -1235,9 +1235,9 @@ static TCGReg tcg_out_arg_reg64(TCGContext *s, TCGReg argreg, #define TLB_SHIFT (CPU_TLB_ENTRY_BITS + CPU_TLB_BITS) -/* We expect to use a 20-bit unsigned offset from ENV. */ -QEMU_BUILD_BUG_ON(offsetof(CPUArchState, tlb_.f[NB_MMU_MODES - 1].table) - > 0xfffff); +/* We expect to use an 9-bit sign-magnitude negative offset from ENV. */ +QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) > 0); +QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) < -256); /* Load and compare a TLB entry, leaving the flags set. Returns the register containing the addend of the tlb entry. Clobbers R0, R1, R2, TMP. */ @@ -1247,39 +1247,15 @@ static TCGReg tcg_out_tlb_read(TCGContext *s, TCGReg addrlo, TCGReg addrhi, { int cmp_off = (is_load ? offsetof(CPUTLBEntry, addr_read) : offsetof(CPUTLBEntry, addr_write)); - int mask_off = offsetof(CPUArchState, tlb_.f[mem_index].mask); - int table_off = offsetof(CPUArchState, tlb_.f[mem_index].table); - TCGReg mask_base = TCG_AREG0, table_base = TCG_AREG0; + int fast_off = TLB_MASK_TABLE_OFS(mem_index); + int mask_off = fast_off + offsetof(CPUTLBDescFast, mask); + int table_off = fast_off + offsetof(CPUTLBDescFast, table); unsigned s_bits = opc & MO_SIZE; unsigned a_bits = get_alignment_bits(opc); - if (table_off > 0xfff) { - int mask_hi = mask_off & ~0xfff; - int table_hi = table_off & ~0xfff; - int rot; - - table_base = TCG_REG_R2; - if (mask_hi == table_hi) { - mask_base = table_base; - } else if (mask_hi) { - mask_base = TCG_REG_TMP; - rot = encode_imm(mask_hi); - assert(rot >= 0); - tcg_out_dat_imm(s, COND_AL, ARITH_ADD, mask_base, TCG_AREG0, - rotl(mask_hi, rot) | (rot << 7)); - } - rot = encode_imm(table_hi); - assert(rot >= 0); - tcg_out_dat_imm(s, COND_AL, ARITH_ADD, table_base, TCG_AREG0, - rotl(table_hi, rot) | (rot << 7)); - - mask_off -= mask_hi; - table_off -= table_hi; - } - /* Load tlb_mask[mmu_idx] and tlb_table[mmu_idx]. */ - tcg_out_ld(s, TCG_TYPE_I32, TCG_REG_TMP, mask_base, mask_off); - tcg_out_ld(s, TCG_TYPE_I32, TCG_REG_R2, table_base, table_off); + tcg_out_ld(s, TCG_TYPE_I32, TCG_REG_TMP, TCG_AREG0, mask_off); + tcg_out_ld(s, TCG_TYPE_I32, TCG_REG_R2, TCG_AREG0, table_off); /* Extract the tlb index from the address into TMP. */ tcg_out_dat_reg(s, COND_AL, ARITH_AND, TCG_REG_TMP, TCG_REG_TMP, addrlo, diff --git a/tcg/i386/tcg-target.inc.c b/tcg/i386/tcg-target.inc.c index 1bd33389c9..f9598b7593 100644 --- a/tcg/i386/tcg-target.inc.c +++ b/tcg/i386/tcg-target.inc.c @@ -1654,10 +1654,12 @@ static inline void tcg_out_tlb_load(TCGContext *s, TCGReg addrlo, TCGReg addrhi, TARGET_PAGE_BITS - CPU_TLB_ENTRY_BITS); tcg_out_modrm_offset(s, OPC_AND_GvEv + trexw, r0, TCG_AREG0, - offsetof(CPUArchState, tlb_.f[mem_index].mask)); + TLB_MASK_TABLE_OFS(mem_index) + + offsetof(CPUTLBDescFast, mask)); tcg_out_modrm_offset(s, OPC_ADD_GvEv + hrexw, r0, TCG_AREG0, - offsetof(CPUArchState, tlb_.f[mem_index].table)); + TLB_MASK_TABLE_OFS(mem_index) + + offsetof(CPUTLBDescFast, table)); /* If the required alignment is at least as large as the access, simply copy the address and mask. For lesser alignments, check that we don't diff --git a/tcg/mips/tcg-target.inc.c b/tcg/mips/tcg-target.inc.c index b827579317..55d8cdf4c9 100644 --- a/tcg/mips/tcg-target.inc.c +++ b/tcg/mips/tcg-target.inc.c @@ -1201,6 +1201,10 @@ static int tcg_out_call_iarg_reg2(TCGContext *s, int i, TCGReg al, TCGReg ah) return i; } +/* We expect to use a 16-bit negative offset from ENV. */ +QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) > 0); +QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) < -32768); + /* * Perform the tlb comparison operation. * The complete host address is placed in BASE. @@ -1214,42 +1218,17 @@ static void tcg_out_tlb_load(TCGContext *s, TCGReg base, TCGReg addrl, unsigned s_bits = opc & MO_SIZE; unsigned a_bits = get_alignment_bits(opc); int mem_index = get_mmuidx(oi); - int mask_off = offsetof(CPUArchState, tlb_.f[mem_index].mask); - int table_off = offsetof(CPUArchState, tlb_.f[mem_index].mask); + int fast_off = TLB_MASK_TABLE_OFS(mem_index); + int mask_off = fast_off + offsetof(CPUTLBDescFast, mask); + int table_off = fast_off + offsetof(CPUTLBDescFast, table); int add_off = offsetof(CPUTLBEntry, addend); int cmp_off = (is_load ? offsetof(CPUTLBEntry, addr_read) : offsetof(CPUTLBEntry, addr_write)); - TCGReg mask_base = TCG_AREG0, table_base = TCG_AREG0; target_ulong mask; - if (table_off > 0x7fff) { - int mask_hi = mask_off - (int16_t)mask_off; - int table_hi = table_off - (int16_t)table_off; - - table_base = TCG_TMP1; - if (likely(mask_hi == table_hi)) { - mask_base = table_base; - tcg_out_opc_imm(s, OPC_LUI, mask_base, TCG_REG_ZERO, mask_hi >> 16); - tcg_out_opc_reg(s, ALIAS_PADD, mask_base, mask_base, TCG_AREG0); - mask_off -= mask_hi; - table_off -= mask_hi; - } else { - if (mask_hi != 0) { - mask_base = TCG_TMP0; - tcg_out_opc_imm(s, OPC_LUI, - mask_base, TCG_REG_ZERO, mask_hi >> 16); - tcg_out_opc_reg(s, ALIAS_PADD, - mask_base, mask_base, TCG_AREG0); - } - table_off -= mask_off; - mask_off -= mask_hi; - tcg_out_opc_imm(s, ALIAS_PADDI, table_base, mask_base, mask_off); - } - } - /* Load tlb_mask[mmu_idx] and tlb_table[mmu_idx]. */ - tcg_out_ld(s, TCG_TYPE_PTR, TCG_TMP0, mask_base, mask_off); - tcg_out_ld(s, TCG_TYPE_PTR, TCG_TMP1, table_base, table_off); + tcg_out_ld(s, TCG_TYPE_PTR, TCG_TMP0, TCG_AREG0, mask_off); + tcg_out_ld(s, TCG_TYPE_PTR, TCG_TMP1, TCG_AREG0, table_off); /* Extract the TLB index from the address into TMP3. */ tcg_out_opc_sa(s, ALIAS_TSRL, TCG_TMP3, addrl, diff --git a/tcg/ppc/tcg-target.inc.c b/tcg/ppc/tcg-target.inc.c index 1f717745c1..7e7343bb7b 100644 --- a/tcg/ppc/tcg-target.inc.c +++ b/tcg/ppc/tcg-target.inc.c @@ -1505,6 +1505,10 @@ static void * const qemu_st_helpers[16] = { [MO_BEQ] = helper_be_stq_mmu, }; +/* We expect to use a 16-bit negative offset from ENV. */ +QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) > 0); +QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) < -32768); + /* Perform the TLB load and compare. Places the result of the comparison in CR7, loads the addend of the TLB into R3, and returns the register containing the guest address (zero-extended into R4). Clobbers R0 and R2. */ @@ -1517,31 +1521,15 @@ static TCGReg tcg_out_tlb_read(TCGContext *s, TCGMemOp opc, = (is_read ? offsetof(CPUTLBEntry, addr_read) : offsetof(CPUTLBEntry, addr_write)); - int mask_off = offsetof(CPUArchState, tlb_.f[mem_index].mask); - int table_off = offsetof(CPUArchState, tlb_.f[mem_index].table); - TCGReg mask_base = TCG_AREG0, table_base = TCG_AREG0; + int fast_off = TLB_MASK_TABLE_OFS(mem_index); + int mask_off = fast_off + offsetof(CPUTLBDescFast, mask); + int table_off = fast_off + offsetof(CPUTLBDescFast, table); unsigned s_bits = opc & MO_SIZE; unsigned a_bits = get_alignment_bits(opc); - if (table_off > 0x7fff) { - int mask_hi = mask_off - (int16_t)mask_off; - int table_hi = table_off - (int16_t)table_off; - - table_base = TCG_REG_R4; - if (mask_hi == table_hi) { - mask_base = table_base; - } else if (mask_hi) { - mask_base = TCG_REG_R3; - tcg_out32(s, ADDIS | TAI(mask_base, TCG_AREG0, mask_hi >> 16)); - } - tcg_out32(s, ADDIS | TAI(table_base, TCG_AREG0, table_hi >> 16)); - mask_off -= mask_hi; - table_off -= table_hi; - } - /* Load tlb_mask[mmu_idx] and tlb_table[mmu_idx]. */ - tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_R3, mask_base, mask_off); - tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_R4, table_base, table_off); + tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_R3, TCG_AREG0, mask_off); + tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_R4, TCG_AREG0, table_off); /* Extract the page index, shifted into place for tlb index. */ if (TCG_TARGET_REG_BITS == 32) { diff --git a/tcg/riscv/tcg-target.inc.c b/tcg/riscv/tcg-target.inc.c index c1f9c784bc..3198e16486 100644 --- a/tcg/riscv/tcg-target.inc.c +++ b/tcg/riscv/tcg-target.inc.c @@ -961,6 +961,10 @@ static void * const qemu_st_helpers[16] = { /* We don't support oversize guests */ QEMU_BUILD_BUG_ON(TCG_TARGET_REG_BITS < TARGET_LONG_BITS); +/* We expect to use a 12-bit negative offset from ENV. */ +QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) > 0); +QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) < -(1 << 11)); + static void tcg_out_tlb_load(TCGContext *s, TCGReg addrl, TCGReg addrh, TCGMemOpIdx oi, tcg_insn_unit **label_ptr, bool is_load) @@ -970,32 +974,11 @@ static void tcg_out_tlb_load(TCGContext *s, TCGReg addrl, unsigned a_bits = get_alignment_bits(opc); tcg_target_long compare_mask; int mem_index = get_mmuidx(oi); - int mask_off, table_off; + int fast_ofs = TLB_MASK_TABLE_OFS(mem_index); + int mask_ofs = fast_ofs + offsetof(CPUTLBDescFast, mask); + int table_ofs = fast_ofs + offsetof(CPUTLBDescFast, table); TCGReg mask_base = TCG_AREG0, table_base = TCG_AREG0; - mask_off = offsetof(CPUArchState, tlb_.f[mem_index].mask); - table_off = offsetof(CPUArchState, tlb_.f[mem_index].table); - if (table_off > 0x7ff) { - int mask_hi = mask_off - sextreg(mask_off, 0, 12); - int table_hi = table_off - sextreg(table_off, 0, 12); - - if (likely(mask_hi == table_hi)) { - mask_base = table_base = TCG_REG_TMP1; - tcg_out_opc_upper(s, OPC_LUI, mask_base, mask_hi); - tcg_out_opc_reg(s, OPC_ADD, mask_base, mask_base, TCG_AREG0); - mask_off -= mask_hi; - table_off -= mask_hi; - } else { - mask_base = TCG_REG_TMP0; - table_base = TCG_REG_TMP1; - tcg_out_opc_upper(s, OPC_LUI, mask_base, mask_hi); - tcg_out_opc_reg(s, OPC_ADD, mask_base, mask_base, TCG_AREG0); - table_off -= mask_off; - mask_off -= mask_hi; - tcg_out_opc_imm(s, OPC_ADDI, table_base, mask_base, mask_off); - } - } - tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP0, mask_base, mask_off); tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_TMP1, table_base, table_off); diff --git a/tcg/s390/tcg-target.inc.c b/tcg/s390/tcg-target.inc.c index 3a8794d9bd..6eefef53a1 100644 --- a/tcg/s390/tcg-target.inc.c +++ b/tcg/s390/tcg-target.inc.c @@ -1537,9 +1537,9 @@ static void tcg_out_qemu_st_direct(TCGContext *s, TCGMemOp opc, TCGReg data, #if defined(CONFIG_SOFTMMU) #include "tcg-ldst.inc.c" -/* We're expecting to use a 20-bit signed offset on the tlb memory ops. */ -QEMU_BUILD_BUG_ON(offsetof(CPUArchState, tlb_.f[NB_MMU_MODES - 1].table) - > 0x7ffff); +/* We're expecting to use a 20-bit negative offset on the tlb memory ops. */ +QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) > 0); +QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) < -(1 << 19)); /* Load and compare a TLB entry, leaving the flags set. Loads the TLB addend into R2. Returns a register with the santitized guest address. */ @@ -1550,8 +1550,9 @@ static TCGReg tcg_out_tlb_read(TCGContext* s, TCGReg addr_reg, TCGMemOp opc, unsigned a_bits = get_alignment_bits(opc); unsigned s_mask = (1 << s_bits) - 1; unsigned a_mask = (1 << a_bits) - 1; - int mask_off = offsetof(CPUArchState, tlb_.f[mem_index].mask); - int table_off = offsetof(CPUArchState, tlb_.f[mem_index].table); + int fast_off = TLB_MASK_TABLE_OFS(mem_index); + int mask_off = fast_off + offsetof(CPUTLBDescFast, mask); + int table_off = fast_off + offsetof(CPUTLBDescFast, table); int ofs, a_off; uint64_t tlb_mask; diff --git a/tcg/sparc/tcg-target.inc.c b/tcg/sparc/tcg-target.inc.c index be10124e11..fe7524a802 100644 --- a/tcg/sparc/tcg-target.inc.c +++ b/tcg/sparc/tcg-target.inc.c @@ -1061,6 +1061,11 @@ static void tcg_out_nop_fill(tcg_insn_unit *p, int count) } #if defined(CONFIG_SOFTMMU) + +/* We expect to use a 13-bit negative offset from ENV. */ +QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) > 0); +QEMU_BUILD_BUG_ON(TLB_MASK_TABLE_OFS(0) < -(1 << 12)); + /* Perform the TLB load and compare. Inputs: @@ -1077,9 +1082,9 @@ static void tcg_out_nop_fill(tcg_insn_unit *p, int count) static TCGReg tcg_out_tlb_load(TCGContext *s, TCGReg addr, int mem_index, TCGMemOp opc, int which) { - int mask_off = offsetof(CPUArchState, tlb_.f[mem_index].mask); - int table_off = offsetof(CPUArchState, tlb_.f[mem_index].table); - TCGReg base = TCG_AREG0; + int fast_off = TLB_MASK_TABLE_OFS(mem_index); + int mask_off = fast_off + offsetof(CPUTLBDescFast, mask); + int table_off = fast_off + offsetof(CPUTLBDescFast, table); const TCGReg r0 = TCG_REG_O0; const TCGReg r1 = TCG_REG_O1; const TCGReg r2 = TCG_REG_O2; @@ -1087,26 +1092,9 @@ static TCGReg tcg_out_tlb_load(TCGContext *s, TCGReg addr, int mem_index, unsigned a_bits = get_alignment_bits(opc); tcg_target_long compare_mask; - if (!check_fit_i32(table_off, 13)) { - int table_hi; - - base = r1; - if (table_off <= 2 * 0xfff) { - table_hi = 0xfff; - tcg_out_arithi(s, base, TCG_AREG0, table_hi, ARITH_ADD); - } else { - table_hi = table_off & ~0x3ff; - tcg_out_sethi(s, base, table_hi); - tcg_out_arith(s, base, TCG_AREG0, base, ARITH_ADD); - } - mask_off -= table_hi; - table_off -= table_hi; - tcg_debug_assert(check_fit_i32(mask_off, 13)); - } - /* Load tlb_mask[mmu_idx] and tlb_table[mmu_idx]. */ - tcg_out_ld(s, TCG_TYPE_PTR, r0, base, mask_off); - tcg_out_ld(s, TCG_TYPE_PTR, r1, base, table_off); + tcg_out_ld(s, TCG_TYPE_PTR, r0, TCG_AREG0, mask_off); + tcg_out_ld(s, TCG_TYPE_PTR, r1, TCG_AREG0, table_off); /* Extract the page index, shifted into place for tlb index. */ tcg_out_arithi(s, r2, addr, TARGET_PAGE_BITS - CPU_TLB_ENTRY_BITS,